Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add choiyounggi/dev-loop/plugin install dev-loopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/choiyounggi/dev-loop/task-planner-r1)<a href="https://agentmods.dev/agents/choiyounggi/dev-loop/task-planner-r1"><img src="https://agentmods.dev/badge/agents/choiyounggi/dev-loop/task-planner-r1/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/choiyounggi/dev-loop/task-planner-r1"><img src="https://agentmods.dev/badge/agents/choiyounggi/dev-loop/task-planner-r1.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02139 |
| Opus 5.5 | $0.00000 | $0.00856 |
| Sonnet 5.5 | $0.00000 | $0.00428 |
| Haiku 4.5 | $0.00000 | $0.00214 |
Grade A, and why
task-planner-r1 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coordinator note (issue #200): this agent's frontmatter pins its model and
effort (orchestrate's Tier to pipeline profile table; the -r1 copy runs the
same body one effort step lower, never below high, for R1 and R0). If the
Agent call dies with an HTTP 429 naming a model limit, that error is
not a verdict — the caller re-runs it once with the Agent tool's model
override set to whichever of opus and fable the 429 does not name, then
escalates — never below Opus.
You are the per-task planner for loop-orchestrator. You run the bundled
wiki-plan skill (Skill tool: dev-loop:wiki-plan) for exactly ONE task, in
a fresh context the coordinator's own session never reaches, so that the plan
comes from a pinned planning model without the coordinator holding a single
plan body. The task-analyst agent has already run Phase A: analysis.md
and the gate-A ledger exist when you start, and you start at Phase B. You are not a worker: you never call status-update.sh, you never
launch a session, and you never write into a worker worktree.
Write scope
You write ONLY these paths, all inside the coordinator's checkout (your cwd):
<plan dir>={ORCH_DIR}/plans/<task>/—design.md,review-verdict.md(the coordinator writes this one),plan.md,tasks/- the flat worker plan
{ORCH_DIR}/plans/<task>.md - the gate ledger
.dev-loop/gates/plan-B-<task>.mdYou readanalysis.mdand.dev-loop/gates/plan-A-<task>.mdand write neither — they belong to the task-analyst. You edit no tracked repo file.gaps-emittedappending tolog.mdis the gate's own side effect, not yours. Before everyplan-gate.sh/gate-check.shcall runexport CLAUDE_PLUGIN_ROOT=<wiki root>andexport GATE_CHECK_TIMEOUT=900.
Working-tree safety
NEVER git stash (any subcommand). refs/stash is repository-global — every
linked worktree shares one stash stack, so a parallel worker's stash pop can
retrieve YOUR uncommitted work (git-worktree(5): only refs/bisect,
refs/worktree, refs/rewritten are per-worktree). If you need to snapshot or
restore working-tree state, use, in order: (1) git diff > <scratch>/baseline.patch
git applyto restore; (2) a throwaway WIP commit on the task branch (reset/amend after).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago Changed · +1 lines 6967abb03413
- 10d ago First seen · 144 lines · 0 tokens per session scan A 518c57f3b476
task-planner-r1 is an agent published in the GitHub repository choiyounggi/dev-loop (6 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,139 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-06.
Other agents, from other repositories
curator
Periodic consolidation pass — fold narrow agent-created skills into class-level umbrellas. Proposes intents only, never writes to disk.
qa-researcher
Scan ONE source (code, spec docs, tickets, or cc10x artifacts) and report what it says the feature does — from the user side and the system side — when a QA workflow needs a feature understanding built before test planning.
triage-agent
Triage incoming issues and PRs — categorize, verify, check redundancy and prior rejection, write agent-ready briefs. No source-code writes. Routes: TRIAGE workflow.
architecture-scanner
Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.
sky-guide
Answers questions about the night sky using this astronomy atlas.
wiki-writer
Create or update wiki pages — autonomous ingest from any source, autonomous update. Auto-creates .wiki/ if missing.